… similarity scores between pairs of peptides. For each pair, a similarity score is composed of
multiple sub-scores … influence that each sub-score will have on the cumulative score. In turn, it …

… by its similarity to a set of known peptide–MHC binders … peptide can be considered a binder
if it has a score within the range of scores of the peptides known to bind to the relevant MHC …

… for assigning weights to similar peptides as opposed to eliminating similar peptides from
the … The LA kernel measures the similarity between two sequences by adding up the scores …

… scoring reflects the frequency of the respective amino acid in natural MHC ligands, T-cell
epitopes, or binding peptides … Our results do, however, suggest that HMMs provide similar …

… peptide sequence (query) to a given MHC molecule is linked to its similarity to a group of
aligned peptides … identify potential binders, we score all the peptide sequences included in the …

… Similar to our result based on murine data (Figure 4A), the human epitopes had a much
higher score in the immunogenicity model than the non-epitopes (Wilcoxon rank-sum test: p = …

… scores can be calculated from observed amino-acid frequencies in each position or be set
manually. The sum of the scores for a given peptide … From the similar behavior of these three …

… Others base similar scoring matrices on multiple peptide … similar to our previous effort
for MHC class I molecules [38]. We present a large dataset of unpublished MHC class II-peptide …

… a broad estimate of their similarity. However, for most proteins, notably for MHC, peptide–protein …
For this reason, we propose to use the F1 score to evaluate our method's discriminative …

… Our results indicate that, at least for peptide:MHC class I binding predictions, scoring
matrices can provide competitive prediction performances. This close prediction performances …